#!/usr/bin/env bash
# Kimi-K3 PD 分离部署（MoonCake RDMA）实验配置。
# 服务器生命周期走 deploy_pd.sh 编排脚本 + deploy profiles：
#   - P 组 profile: pro6000/kimi3_pro6000_pd_prefill
#   - D 组 profile: pro6000/kimi3_pro6000_pd_decode
#   - 编排: experiments/pro6000/kimi3_pro6000_pd_rdma/deploy_pd.sh
# 部署参数以 profile / deploy_pd.sh 为准，勿在此重复。

EXPERIMENT="kimi3_pro6000_pd_rdma"
MODEL_NAME="Kimi-K3"
MODEL_PATH="/data/hf_models/Kimi-K3"
SERVED_MODEL_NAME="kimi-k3"

# Router (MiniLB) 入口端口。
SGLANG_PORT="${SGLANG_PORT:-31000}"

# MoonCake master 地址（P 组头节点）。
MOONCAKE_MASTER="${MOONCAKE_MASTER:-174.1.60.1:50051}"

# Python interpreter for orchestration scripts.
# VENV_CLIENT: 不用 native client（本环境无 sglang.bench_serving），改用 docker client

# Run the benchmark client natively (0) or inside Docker (1).
USE_DOCKER_CLIENT="${USE_DOCKER_CLIENT:-1}"

# Benchmark client: 复用 kimi-k3 镜像（内含 sglang.bench_serving）。
DOCKER_CLIENT_IMAGE="${DOCKER_CLIENT_IMAGE:-lmsysorg/sglang:kimi-k3}"

# Deployment profiles used by deploy_pd.sh.
P_DEPLOY_PROFILE="${P_DEPLOY_PROFILE:-pro6000/kimi3_pro6000_pd_prefill}"
D_DEPLOY_PROFILE="${D_DEPLOY_PROFILE:-pro6000/kimi3_pro6000_pd_decode}"

# Per-scenario timeout to avoid hangs (seconds).
SCENARIO_TIMEOUT_S="${SCENARIO_TIMEOUT_S:-3600}"